Match features (ORB)

POST /api/image-match-features

Detect and match feature points between two images. Robust to rotation, scale, and modest lighting changes. Useful for image alignment and panorama stitching.

Detects feature points in two images and finds correspondences between them. The matching is robust to rotation, scale, and modest lighting differences — much more flexible than pixel- level template matching. Useful for image alignment, panorama stitching, motion estimation, and object-pose estimation. Returns each matched pair as `{(x1, y1), (x2, y2), distance}` where distance is the descriptor similarity.

Inputs

Name	Type	Default	Description
image*	file	—	Query image bytes.
target*	file	—	Train image bytes — the second image to match against.
nfeatures	number (50…8000)	1000	Max ORB keypoints per image.
maxMatches	number (1…1000)	50	Cap on returned match pairs.

Response

Modes: json. Cache: yes (24h TTL).